97 accepted papers
In this work, we investigate the synergy between supervised fine-tuning (SFT) and reinforcement learning (RL) in developing strong reasoning models. We begin by curating the SFT training data through two scaling strategies: increasing the number of collected prompts and the number of generated respo…
Effective multi-agent coordination requires aligning incentives while adhering to complex requirements. However, real-world systems often impose situational constraints, context-dependent requirements triggered only under specific conditions, which challenge standard Correlated Equilibria (CE) solut
While adversarial fine-tuning can enhance the robustness of vision-language models (VLMs), such approaches are computationally expensive. Adversarial prompt tuning has emerged as a practical alternative. However, existing methods are limited by their reliance on vulnerable continuous image features.…
This paper presents a simple, effective, and cost-efficient strategy, named ModelSwitch, to improve LLM performance by scaling test-time compute. ModelSwitch builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage the
Vision-Language Models (VLMs) have emerged as versatile solutions for zero-shot question answering (QA) across various domains. However, enabling VLMs to effectively comprehend structured graphs and perform accurate, efficient QA remains challenging. Existing approaches typically rely on a single ty
Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new samples from this space. This characteristic creates an intrinsic
The webpage-to-code task requires models to understand visual representations of webpages and generate corresponding code. However, existing benchmarks primarily focus on static screenshot-to-code tasks, thereby overlooking the dynamic interactions fundamental to real-world web applications. To addr…
Recent multimodal large language models (MLLMs) increasingly integrate multiple vision encoders to improve performance on various benchmarks, assuming that diverse pretraining objectives yield complementary visual signals. However, we show this assumption often fails in practice. Through systematic…
Data Assimilation (DA) aims to integrate observations with model forecasts to estimate the state of dynamical systems. Despite the widespread application of diffusion-based assimilation methods, they remain constrained by the high dimensionality of atmospheric states and the reliance on imperfect st…
The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments across diverse languages. To address this, we introduce **MEnvAgent**, a **M**ult…
The missing of graph attributes poses a significant challenge in graph representation learning. Some existing graph attribute completion methods adopt the shared-space hypothesis or employ end-to-end frameworks to perform single-attribute imputation. However, these models can only generate one singl
Large tensor learning algorithms are typically computationally expensive and require storing a vast amount of data. In this paper, we propose a unified online Riemannian gradient descent (oRGrad) algorithm for tensor learning, which is computationally efficient, consumes much less memory, and can ha…
Generating new Low-Rank Adaptation (LoRA) weights from pre-trained LoRAs has demonstrated strong generalization capabilities across various tasks, enabling the efficient transfer of AI models, particularly on resource-constrained edges. However, previous studies either merge base LoRAs via weighting
Coarse-grained time series (CGTS) are critical for business and macroeconomic analysis. However, CGTS are typically updated infrequently and contain few observations, so model-centric training on raw data is prone to overfitting and degraded forecast accuracy. To address this, we propose SI-CVAE, a
Recent large vision-language models (LVLMs) have demonstrated impressive reasoning ability by generating long chain-of-thought (CoT) responses. However, CoT reasoning in multimodal contexts is highly vulnerable to visual hallucination propagation: once an intermediate reasoning step becomes inconsis
Robust cross-view geo-localization (CVGL) remains challenging despite the surge in recent progress. Existing methods still rely on field-of-view (FoV)-specific training paradigms, where models are optimized under a fixed FoV but collapse when tested on unseen FoVs and unknown orientations. This limi
Basketball players catch fast passes, and porters unload goods with apparent ease. These actions demonstrate how humans rely on intelligent regulation strategies to drive muscle activity. Replicating similar dynamic responses and strong impact absorption in robotics, however, remains a major challen…
Tactile perception is indispensable for robots to implement various manipulations dexterously, especially in contact-rich scenarios. However, alongside with the development of deep learning techniques, it meanwhile suffers from training data scarcity and time-consuming learning process in practical …
In this paper, we introduce AceMath, a suite of frontier math models that excel in solving complex math problems, along with highly effective reward models capable of evaluating generated solutions and reliably identifying the correct ones. To develop the instruction-tuned math models, we propose a…
Despite recent progress in large-scale reinforcement learning (RL) for reasoning, the training recipe for building high-performing reasoning models remains elusive. Key implementation details of frontier models, such as DeepSeek-R1, including data curation strategies and RL training recipe, are ofte…
Insect-scale flapping-wing micro aerial vehicles (FWMAVs) employing piezoelectric direct-drive configurations eliminate traditional kinematic chains through direct coupling of the wing and actuator. While this design approach significantly reduces structural complexity and manufacturing costs compar
Learning optimal policies in multi-agent cooperative settings with visual observations is significant and challenging. Agents must first perform state representation learning for their image observations and then learn policies in the abstracted state space. Aiming at this problem, we propose a nove…
Diffusion-based text-to-audio (TTA) generation has made substantial progress, leveraging latent diffusion model (LDM) to produce high-quality, diverse and instruction-relevant audios. However, beyond generation, the task of audio editing remains equally important but has received comparatively littl…
Point cloud completion, aiming to reconstruct missing part from incomplete point clouds, is a pivotal task in 3D computer vision. Traditional supervised approaches often necessitate complete point clouds for training supervision, which are not readily accessible in real-world applications. Recent st…
Dual-energy CT exploits the different attenuation characteristics of substances under different energy X-rays and collects high- and low-energy data from the same area to differentiate and quantify specific substances, which is now widely used in clinical diagnosis, disease monitoring, and other fie…
Face swapping transfers the identity of a source face to a target face while retaining the attributes like expression, pose, hair, and background of the target face. Advanced face swapping methods have achieved attractive results. However, these methods often inadvertently transfer identity informat…
Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with human preferences. Despite its advantages, DPO suffers from a length bias, generating responses longer than those…
While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of the reasons behind this is the visual encoder used are task-dependent, preventing effective feature extraction in diffe…
Conditional dependency present one of the trickiest problems in Compositional Zero-Shot Learning, leading to significant property variations of the same state (object) across different objects (states). To address this problem, existing approaches often adopt either all-to-one or one-to-one represen
Multimodal emotion recognition in conversation (MERC) aims to identify speakers’ emotional states by utilizing text, audio, and visual modalities. Although recent large language model (LLM)-based methods have demonstrated strong performance, they typically adopt static fusion strategies that integra
Domain adaptation (DA) for cardiac ultrasound image segmentation is clinically significant and valuable. However, previous domain adaptation methods are prone to be affected by the incomplete pseudo label and low-quality target to source images. Human-centric domain adaptation has great advantages o…
Modeling animatable human avatars from videos is a long-standing and challenging problem. While conventional methods require per-instance optimization, recent feed-forward methods have been proposed to generate 3D Gaussians with a learnable network.However, these methods predict independent Gaussian…
Low-Dimension-to-High-Dimension (LDHD) generalization, a subset of Out-of-Distribution (OOD) generalization, involves training on a low-dimensional subspace and testing in a high-dimensional space. Assuming instances are generated from latent variables reflecting problem scale, LDHD generalization c…
Dynamic edge networks revolutionize mobile edge computing by enabling real-time applications in intelligent transportation, augmented reality, and industrial Internet of Things (IoT). Efficient workload offloading in dynamic edge networks is crucial for addressing the increasing demands of time-vary
Multi-agent systems often face challenges such as elevated communication demands and intricate interactions. We propose an innovative hierarchical graph attention actor-critic reinforcement learning method to address the issues, which uses the hierarchical graph attention to capture the relationship…
Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen generalization with prior knowledge from only seen classes and shared semantics. Existing methods typically build the skeleton-semantics interactions by uncontrollable mappings and conspicuous representations, th…
Message-passing graph neural networks (MPNNs) and structural features (SFs) are cornerstones for the link prediction task. However, as a common and intuitive mode of understanding, the potential of visual perception has been overlooked in the MPNN community. For the first time, we equip MPNNs with v…
Reducing radiation doses benefits patients, but the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts. While deep learning (DL) has shown promise in LDCT reconstruction, it requires large-scale data collection from multiple clients, ra…
Recently, large language models (LLMs) and multimodal large language models (MLLMs) have demonstrated promising results on document visual question answering (VQA) task, particularly after training on document instruction datasets. An effective evaluation method for document instruction data is cruc…
While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations. The limited data available on super-aged individuals in exi…
Sequential Resource Allocation with situational constraints presents a significant challenge in real-world applications, where resource demands and priorities are context-dependent. This paper introduces a novel framework, SCRL, to address this problem. We formalize situational constraints as logic
Micro blimps exhibit significant potential for applications in environmental monitoring and disaster rescue. Nonetheless, traditional propulsion methods for micro blimps encounter challenges such as complex mechanical structures, intricate attitude control, and large volumes. This paper present a no
Large language models (LLMs) combined with instruction tuning have shown significant progress in information extraction (IE) tasks, exhibiting strong generalization capabilities to unseen datasets by following annotation guidelines. However, their applicability to low-resource languages remains limi…
Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, which often lead to {\em unstable} training. Recent non-adversarial IRL approach…
Large language models (LLM) have prioritized expanding the context window from which models can incorporate more information. However, training models to handle long contexts presents significant challenges. These include the scarcity of high-quality natural long-context data, the potential for perf…
Dropped Head Syndrome (DHS) causes a passively correctable neck deformation. Currently, there is no wearable orthopedic neck brace to fulfill the needs of persons suffering from DHS. Related works have made progress in this area by creating mobile neck braces that provide head support to mitigate de
Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges when gathering reliable data from the web to build comprehensive training datasets, subsequentl…
Long sequence prediction has broad and significant application value in fields such as finance, wind power, and weather. However, the complex long-term dependencies of long sequence data and the potential domain shift problems limit the effectiveness of traditional models in practical scenarios. To…
Although large language models (LLMs) acquire extensive world knowledge and some reasoning abilities, their proficiency in generating humorous sentences remains a challenge. Previous research has demonstrated that the humor generation capabilities of ChatGPT are confined to producing merely 25 uniqu…
Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases, the performance of zero-shot cross-lingual transfer learnin…
Neural population coding can represent continuous information by neurons with a series of discrete preferred stimuli, and we find that the bell-shaped tuning curve plays an important role in this mechanism. Inspired by this, we incorporate a bell-shaped tuning curve into the discrete group convoluti…
Robotic arms are key components in fruit-harvesting robots. In agricultural settings, conventional serial or parallel robotic arms often fall short in meeting the demands for a large workspace, rapid movement, enhanced capability of obstacle avoidance and affordability. This study proposes LingXtend…
"Learning radiance fields (NeRF) with powerful 2D diffusion models has garnered popularity for text-to-3D generation. Nevertheless, the implicit 3D representations of NeRF lack explicit modeling of meshes and textures over surfaces, and such surface-undefined way may suffer from the issues, e.g., no…
"Occupancy prediction plays a pivotal role in autonomous driving. Previous methods typically construct dense 3D volumes, neglecting the inherent sparsity of the scene and suffering high computational costs. To bridge the gap, we introduce a novel fully sparse occupancy network, termed SparseOcc. Spa…
Vision Language Models (VLMs) are rapidly advancing in their capability to answer information-seeking questions. As these models are widely deployed in consumer applications, they could lead to new privacy risks due to emergent abilities to identify people in photos, geolocate images, etc. As we dem…
Designing suitable reward functions for numerous interacting intelligent agents is challenging in real-world applications. Inverse reinforcement learning (IRL) in mean field games (MFGs) offers a practical framework to infer reward functions from expert demonstrations. While promising, the assumptio…
Phase retrieval seeks to reconstruct a series of image sequences from measurements that only capture their magnitudes. Current approaches either flatten and stack the image sequences, disregarding their multidimensional structural information, or fail to account for errors within the sensing vectors…
Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle each part completely, which means the edited parts will affect the others, resulting in poor diversity and fidelity. In…
Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: *how do these models acquire an understanding of world hybrid relations?* Traditional statistical learning, particularly for prediction problems, may overlook the…
Current research for node classification focuses on dealing with either graph noise or label noise, but few studies consider both of them. In this paper, we propose a new robust node classification method to simultaneously deal with graph noise and label noise. To do this, we design a graph contrast…
Topic relevance of an essay demands that the composition adheres to a clear theme and aligns well with the essay prompt requirements, a critical aspect of essay quality evaluation. However, existing research of Automatic Essay Scoring (AES) for Chinese essays has overlooked topic relevance and lacks…
"Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or finding a similar photo with a query image. To approach such…
Recent innovations on text-to-3D generation have featured Score Distillation Sampling (SDS) which enables the zero-shot learning of implicit 3D models (NeRF) by directly distilling prior knowledge from 2D diffusion models. However current SDS-based models still struggle with intricate text prompts a…
Incremental object detection (IOD) task requires a model to learn continually from newly added data. However, directly fine-tuning a well-trained detection model on a new task will sharply decrease the performance on old tasks, which is known as catastrophic forgetting. Knowledge distillation, inclu…
This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By training on intervals, all the perturbed images that are mapped to the same int…
Pre-trained vision and language models have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering. However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual co…
Translating training data into many languages has emerged as a practical solution for improving cross-lingual transfer. For tasks that involve span-level annotations, such as information extraction or question answering, an additional label projection step is required to map annotated spans onto the…
Learning inter-image similarity is crucial for 3D medical images self-supervised pre-training, due to their sharing of numerous same semantic regions. However, the lack of the semantic prior in metrics and the semantic-independent variation in 3D medical images make it challenging to get a reliable…
Survival prediction based on whole slide images (WSIs) is a challenging task for patient-level multiple instance learning (MIL). Due to the vast amount of data for a patient (one or multiple gigapixels WSIs) and the irregularly shaped property of WSI, it is difficult to fully explore spatial, contex…
We present a human-in-the-loop evaluation framework for fact-checking novel misinformation claims and identifying social media messages that support them. Our approach extracts check-worthy claims, which are aggregated and ranked for review. Stance classifiers are then used to identify tweets suppor…
Gigapixel Whole Slide Images (WSIs) aided patient diagnosis and prognosis analysis are promising directions in computational pathology. However, limited by expensive and time-consuming annotation costs, WSIs usually only have weak annotations, including 1) WSI-level Annotations (WA) and 2) Limited P…
Non-intrusive load monitoring (NILM) aims to decompose aggregated electrical usage signal into appliance-specific power consumption and it amounts to a classical example of blind source separation tasks. Leveraging recent progress on deep learning techniques, we design a new neural NILM model {\em M…
Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong generalization on various visual domains and tasks. However, existing image classification benchmarks often evaluate recognition on a specific domain (e.g., outdoor images) or a specific task (e.g., classifying plant sp…
Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy holds when pre-training a foundation model. However, the fou…
Multi-channel imaging data is a prevalent data format in scientific fields such as astronomy and biology. The structured information and the high dimensionality of these 3-D tensor data makes the analysis an intriguing but challenging topic for statisticians and practitioners. The low-rank scalar-on…
Tissue segmentation is a critical task in computational pathology due to its desirable ability to indicate the prognosis of cancer patients. Currently, numerous studies attempt to use image-level labels to achieve pixel-level segmentation to reduce the need for fine annotations. However, most of the…
The rapid development of facial manipulation techniques has aroused public concerns in recent years. Existing deepfake video detection approaches attempt to capture the discrim- inative features between real and fake faces based on tem- poral modelling. However, these works impose supervisions on sp…
"Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time step of denoising process. However, due to the ability of th…
With the rapid development of facial forgery techniques, forgery detection has attracted more and more attention due to security concerns. Existing approaches attempt to use frequency information to mine subtle artifacts under high-quality forged faces. However, the exploitation of frequency informa…
"With the rapid development of Deepfake techniques, the capacity of generating hyper-realistic faces has aroused public concerns in recent years. The temporal inconsistency which derives from the contrast of facial movements between pristine and forged videos can serve as an efficient cue in identif…
Effective multi-hop question answering (QA) requires reasoning over multiple scattered paragraphs and providing explanations for answers. Most existing approaches cannot provide an interpretable reasoning process to illustrate how these models arrive at an answer. In this paper, we propose a Questio…
The nature of thick-slice scanning causes severe inter-slice discontinuities of 3D medical images, and the vanilla 2D/3D convolutional neural networks (CNNs) fail to represent sparse inter-slice information and dense intra-slice information in a balanced way, leading to severe underfitting to inter-…
Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has performed the desired reasoning to reach the correct answer. M…
Recently, deep learning techniques have been extensively studied for pansharpening, which aims to generate a high resolution multispectral (HRMS) image by fusing a low resolution multispectral (LRMS) image with a high resolution panchromatic (PAN) image. However, existing deep learning-based panshar…
The rapid development of face forgery techniques has drawn growing attention due to security concerns. Existing deepfake video detection methods always attempt to capture the discriminative features by directly exploiting static temporal convolution to mine temporal inconsistency, without explicit…
As an essential step in the pathological diagnosis, histochemical staining can show specific tissue structure information and, consequently, assist pathologists in making accurate diagnoses. Clinical kidney histopathological analyses usually employ more than one type of staining: H&E, MAS, PAS, PASM…
Mainstream state-of-the-art domain generalization algorithms tend to prioritize the assumption on semantic invariance across domains. Meanwhile, the inherent intra-domain style invariance is usually underappreciated and put on the shelf. In this paper, we reveal that leveraging intra-domain style in…
With the rapid development of facial manipulation techniques, face forgery has received considerable attention in digital media forensics due to security concerns. Most existing methods formulate face forgery detection as a classification problem and utilize binary labels or manipulated region masks…
Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities. In the zero-shot transfer setting, only English training data is used, and the fine-tuned model is evaluated on another target language. While this…
Multiple instance learning (MIL) is a powerful tool to solve the weakly supervised classification in whole slide image (WSI) based pathology diagnosis. However, the current MIL methods are usually based on independent and identical distribution hypothesis, thus neglect the correlation among differen…
In this paper, we propose and evaluate a novel human-machine interface (HMI) for controlling a standing mobility vehicle or person carrier robot, aiming for a hands-free control through upper-body natural postures derived from gaze tracking while walking. We target users with lower-body impairment w…
Deep learning-based medical image registration and segmentation joint models utilize the complementarity (augmentation data or weakly supervised data from registration, region constraints from segmentation) to bring mutual improvement in complex scene and few-shot situation. However, further adoptio…
We present an attention-weighted loss in a photometric stereo neural network to improve 3D surface recovery accuracy in complex-structured areas, such as edges and crinkles, where existing learning-based methods often failed. Instead of using a uniform penalty for all pixels, our method employs the…
In this paper, we propose a solution to transforming photos of real-world scenes into cartoon style images, which is valuable and challenging in computer vision and computer graphics. Our solution belongs to learning based methods, which have recently become popular to stylize images in artistic for…
Image retargeting techniques that adjust images into different sizes have attracted much attention recently. Objective quality assessment (OQA) of image retargeting results is often desired to automatically select the best results. Existing OQA methods output an absolute score for each retargeted im…
A novel retinal vessel enhancement method based on multi-dictionary and sparse coding is proposed in this paper. Two dictionaries are utilized to gain the retinal vascular structures and details, one is the representation dictionary (RD) generated from the original retinal images, and another is the…
Many computer vision problems can be posed as learning a low-dimensional subspace from high dimensional data. The low rank matrix factorization (LRMF) represents a commonly utilized subspace learning strategy. Most of the current LRMF techniques are constructed on the optimization problem using L_1…